Adaptive Model Predictive Control by Learning Classifiers

TL;DR

This paper introduces an adaptive model predictive control method that learns classifiers to estimate control and model parameters, enhancing robustness in robotics tasks with uncertainties and disturbances.

Contribution

It presents a novel adaptive MPC approach that integrates classifier-based density ratio estimation with Bayesian optimization for improved control under uncertainty.

Findings

Effective in classical control problems with model uncertainty

Robust performance in robotics manipulation tasks

Outperforms traditional MPC in uncertain environments

Abstract

Stochastic model predictive control has been a successful and robust control framework for many robotics tasks where the system dynamics model is slightly inaccurate or in the presence of environment disturbances. Despite the successes, it is still unclear how to best adjust control parameters to the current task in the presence of model parameter uncertainty and heteroscedastic noise. In this paper, we propose an adaptive MPC variant that automatically estimates control and model parameters by leveraging ideas from Bayesian optimisation (BO) and the classical expected improvement acquisition function. We leverage recent results showing that BO can be reformulated via density ratio estimation, which can be efficiently approximated by simply learning a classifier. This is then integrated into a model predictive path integral control framework yielding robust controllers for a variety of challenging robotics tasks. We demonstrate the approach on classical control problems under model uncertainty and robotics manipulation tasks.